Deep learning is combined with massive-scale citizen science to improve large-scale image classification
Deep learning is combined with massive-scale citizen science to improve large-scale image classification
复制标题
DOI：
10.1038/nbt.4225
复制
发表时间：
2018-09-01
影响因子：
46.9
通讯作者：
Lundberg, Emma
中科院分区：
文献类型：
--
作者：
Sullivan, Devin P.;Winsnes, Casper F.;Lundberg, Emma
图像的模式识别和分类是整个生命科学的关键挑战。我们结合了两种方法对荧光显微镜图像进行大规模分类。首先，利用人类蛋白质图谱（HPA）细胞图谱中的公开数据集，我们将图像分类任务作为迷你游戏集成到主流视频游戏（EVE Online）中，名为“Project Discovery”。一年内 322,006 名游戏玩家的参与提供了近 3300 万个亚细胞定位模式分类，包括 HPA 之前未注释的模式。其次，我们使用深度学习构建了自动化本地化细胞注释工具（Loc-CAT）。该工具将蛋白质分为 29 种亚细胞定位模式，并且可以有效地处理多定位蛋白质，在不同的细胞类型中表现强劲。结合游戏玩家的注释和深度学习，我们应用迁移学习创建了一个增强学习器，可以表征亚细胞蛋白质分布，F1 得分为 0.72。我们发现，参与商业电脑游戏的玩家提供的数据可以增强深度学习，并实现可扩展且易于改进的图像分类。
Pattern recognition and classification of images are key challenges throughout the life sciences. We combined two approaches for large-scale classification of fluorescence microscopy images. First, using the publicly available data set from the Cell Atlas of the Human Protein Atlas (HPA), we integrated an image-classification task into a mainstream video game (EVE Online) as a mini-game, named Project Discovery. Participation by 322,006 gamers over 1 year provided nearly 33 million classifications of subcellular localization patterns, including patterns that were not previously annotated by the HPA. Second, we used deep learning to build an automated Localization Cellular Annotation Tool (Loc-CAT). This tool classifies proteins into 29 subcellular localization patterns and can deal efficiently with multi-localization proteins, performing robustly across different cell types. Combining the annotations of gamers and deep learning, we applied transfer learning to create a boosted learner that can characterize subcellular protein distribution with F1 score of 0.72. We found that engaging players of commercial computer games provided data that augmented deep learning and enabled scalable and readily improved image classification.